Vehicle fault detection and maintenance method and device, electronic equipment and storage medium

Abstract

The invention relates to a vehicle fault detection and maintenance method and device, electronic equipment and a storage medium, and belongs to the technical field of vehicle fault detection.The method comprises the steps that historical data of a main locomotive factory and basic operation data of a vehicle are obtained; the basic operation data comprises at least one piece of basic parameter data and a fault code; constructing a knowledge graph based on the historical data; at least one piece of basic parameter data in the basic operation data is diagnosed one by one according to the knowledge graph, and a diagnosis result corresponding to each piece of basic parameter data is obtained; when the diagnosis result is that the fault exists, determining fault parameter data, and correcting the fault parameter data; according to the method, the knowledge graph is constructed, the at least one basic parameter data in the basic operation data is diagnosed one by one through the knowledge graph, the detection efficiency and accuracy of fault diagnosis are improved, and when the fault is detected, the fault parameter data are corrected, so that the fault of the vehicle is repaired in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle fault detection, and in particular to a vehicle fault detection and maintenance method, device, electronic equipment and storage medium. Background Art

[0002] New energy vehicles have become an indispensable part of people's lives. With the rapid development of connected vehicle and artificial intelligence technologies, the types and numbers of modern vehicles are increasing. Modern cars are integrating a growing number of intelligent devices, which have become an essential component of modern vehicles. Vehicle safety has become a primary concern, and improvements in vehicle fault diagnosis technology are essential. However, various faults are inevitable during vehicle use, impacting the owner's experience. As people become more familiar with vehicle structure and maintenance techniques, more and more car owners are taking on their own repairs and maintenance. However, diagnosing vehicle faults often requires considerable effort and time to conduct a thorough inspection of each component.

[0003] In the existing technology, there are two main methods for diagnosing and repairing vehicle parts. One method involves manually operating diagnostic instruments to perform serial diagnosis on each vehicle component, requiring an operator to be present at the vehicle. The other method uses computer technology to remotely detect vehicle parts by issuing diagnostic instructions, and when an anomaly is detected, the user is prompted to perform repairs. However, with the first diagnostic method, the types and number of vehicle parts are diverse and numerous. Relying solely on manual on-site diagnosis takes a long time, and the types and number of faults that can be detected are very limited, resulting in high labor and material costs. The second method, which uses computer technology to diagnose vehicle parts, also has a limited number of faults that can be detected and suffers from false fault detection. Fault accuracy is low, and only a single controller can be tested at a time, lacking the ability to perform concurrent diagnosis and the ability to repair detected faults in real time.

[0004] Therefore, there is an urgent need to propose a vehicle fault detection and maintenance method, device, electronic device and storage medium to solve the technical problems existing in the prior art of low detection efficiency, low accuracy and lack of ability to repair detected faults in real time for vehicle parts fault diagnosis. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle fault detection and maintenance method, device, electronic device and storage medium to solve the technical problems existing in the prior art of low detection efficiency and accuracy in fault diagnosis of vehicle parts, and lack of ability to repair detected faults in real time.

[0006] In order to solve the above problems, the present invention provides a vehicle fault detection and maintenance method, comprising: Obtain historical data from the host vehicle manufacturer and basic operating data of the vehicle; the basic operating data includes at least one basic parameter data and a fault code; Building a knowledge graph based on the historical data; diagnosing the at least one basic parameter data and the fault code in the basic operating data one by one according to the knowledge graph to obtain a diagnosis result corresponding to each basic parameter data; When the diagnosis result indicates that a fault exists, fault parameter data is determined and the fault parameter data is corrected.

[0007] In one possible implementation, constructing a knowledge graph based on the historical data includes: Updating the knowledge base according to the historical data to obtain an initial knowledge base; Construct a diagnosis model based on the fault analysis model, multi-fault reasoning model and fault prediction model; A knowledge graph is constructed based on the diagnostic model and the initial knowledge base.

[0008] In a possible implementation, the historical data includes image data and initial text data, and updating the knowledge base according to the historical data to obtain the initial knowledge base includes: Recognizing the image data to obtain image knowledge; Converting the image knowledge to obtain image text data; Performing knowledge extraction on the initial text data and the image text data respectively to obtain corresponding knowledge ontologies; Performing quality assessment on the knowledge ontology to obtain an assessment result; The target text data with qualified evaluation results is stored in the knowledge base to obtain an initial knowledge base.

[0009] In a possible implementation, the basic operating data further includes at least one key parameter data, and after constructing the knowledge graph based on the historical data, the process further includes: Generate corresponding diagnostic instructions based on the diagnostic SDK and the at least one key parameter data; According to the diagnostic instructions and the knowledge graph, the corresponding key parameter data is deeply diagnosed to obtain a diagnostic result.

[0010] In a possible implementation, the method further includes: When the vehicle breaks down, a fault collection command is determined according to the fault location; According to the fault collection command, a fault code of the vehicle is obtained.

[0011] In a possible implementation, the correcting the fault parameter data includes: When the fault parameter data indicates that a software fault occurs in a component, the software of the component is upgraded based on the OTA technology to obtain an upgraded target software.

[0012] In a possible implementation, the method further includes: Training and updating the knowledge graph according to the basic operation data to obtain an updated knowledge graph; Based on the updated knowledge graph, intelligent after-sales diagnosis of the vehicle is generated.

[0013] On the other hand, the present invention also provides a vehicle fault detection and maintenance device, comprising: A data acquisition module is used to acquire historical data of the host vehicle manufacturer and basic operating data of the vehicle; the basic operating data includes at least one basic parameter data and a fault code; A graph construction module, used to construct a knowledge graph based on the historical data; a diagnosis determination module, configured to diagnose the at least one basic parameter data and the fault code in the basic operating data one by one according to the knowledge graph, and obtain a diagnosis result corresponding to each basic parameter data; The fault correction module is used to determine fault parameter data and correct the fault parameter data when the diagnosis result shows that a fault exists.

[0014] On the other hand, an embodiment of the present invention discloses an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various steps of the above-mentioned vehicle fault detection and maintenance method embodiment are implemented.

[0015] On the other hand, an embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the various steps of the above-mentioned vehicle fault detection and repair method embodiment are implemented.

[0016] The beneficial effects of the present invention are: obtaining historical data of the host vehicle manufacturer and basic operating data of the vehicle; the basic operating data includes at least one basic parameter data and a fault code; constructing a knowledge graph based on the historical data; diagnosing at least one basic parameter data in the basic operating data one by one according to the knowledge graph, and obtaining the diagnosis result corresponding to each basic parameter data; when the diagnosis result is that there is a fault, determining the fault parameter data, and correcting the fault parameter data; the present invention can construct a knowledge graph, and then can diagnose at least one basic parameter data in the basic operating data one by one through the knowledge graph, thereby improving the detection efficiency and accuracy of fault diagnosis, and can also correct the fault parameter data when a fault is detected, so as to repair the vehicle fault in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of an embodiment of a vehicle fault detection and repair method provided by the present invention; Figure 2 For the present invention Figure 1 A schematic flow chart of an embodiment of step S102; Figure 3 For the present invention Figure 2 A schematic flow chart of an embodiment of step S201; Figure 4 A schematic structural diagram of an embodiment of the overall logic diagram for vehicle fault detection and maintenance provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of a vehicle fault detection and maintenance device provided by the present invention; Figure 6 This is a schematic structural diagram of an embodiment of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0019] like Figure 1 As shown, a specific embodiment of the present invention discloses a vehicle fault detection and maintenance method, comprising: S101, obtaining historical data of the host vehicle manufacturer and basic operating data of the vehicle; the basic operating data includes at least one basic parameter data and a fault code; S102. Build a knowledge graph based on historical data; S103: diagnose at least one basic parameter data and fault code in the basic operating data one by one according to the knowledge graph to obtain a diagnosis result corresponding to each basic parameter data; S104: When the diagnosis result shows that a fault exists, determine fault parameter data and correct the fault parameter data.

[0020] In a specific embodiment of the present invention, it can be applied to any vehicle to perform fault detection on the vehicle, and the historical data of the host vehicle manufacturer can be obtained, wherein the historical data may include maintenance manuals, vehicle circuit diagrams, historical maintenance data and other data. The maintenance manuals, vehicle circuit diagrams, historical maintenance data and other information are used to construct knowledge. An intelligent concurrent repair system, i.e., a knowledge graph, can be constructed through fault analysis models, multi-fault reasoning models, fault prediction models, etc. A collection list file of key information is configured in the cloud, and the information to be collected is sent to the vehicle side. The diagnostic SDK software supporting the vehicle side realizes data collection and obtains the basic operation of the vehicle. The cloud then analyzes the data to obtain the required information (i.e. basic operating data). At the same time, it collects and queries the DTC (diagnostic trouble code) in real time to find out the fault information of the parts. Based on the basic operating data and fault information, combined with the knowledge graph, it analyzes the possible causes of the fault and guides the user to troubleshoot step by step until the fault is eliminated. At the same time, it predicts faults based on the collected basic operating data, informs the user in advance of possible faults, and takes preventive measures. It introduces OTA upgrade technology to realize calibration, software upgrade and parameter correction.

[0021] In a specific embodiment of the present invention, a list of parameters that need to be collected is configured in the cloud. These parameters are key information that affects vehicle performance, that is, basic operating data, such as engine temperature and humidity; gearbox temperature, etc.; these parameters can be customized, and the collection cycle and upload frequency are set; they are sent to the vehicle-side tbox in the form of files, and the vehicle-side collects and uploads data according to the collection tasks described in the files; in order to improve the collection efficiency, Ethernet is used for transmission between the tbox and various domain controllers, which improves the data collection efficiency.

[0022] Compared with the prior art, the present embodiment provides a method for obtaining historical data of the host vehicle manufacturer and basic operating data of the vehicle; the basic operating data includes at least one basic parameter data and a fault code; a knowledge graph is constructed based on the historical data; at least one basic parameter data in the basic operating data is diagnosed one by one according to the knowledge graph to obtain a diagnosis result corresponding to each basic parameter data; when the diagnosis result is that a fault exists, the fault parameter data is determined and the fault parameter data is corrected; the present invention can construct a knowledge graph, and then can diagnose at least one basic parameter data in the basic operating data one by one through the knowledge graph, thereby improving the detection efficiency and accuracy of fault diagnosis, and can also correct the fault parameter data when a fault is detected, so as to repair the vehicle fault in real time. Currently, the gateway component has been introduced into the electronic and electrical architecture of intelligent connected vehicles. The gateway can forward the requested message, which can be a one-to-one forwarding of the physical address or a one-to-many forwarding of the logical address, which makes concurrent diagnosis possible. Without the gateway component, when diagnosing multiple controllers, it is necessary to send a heartbeat message to each controller to maintain the connection during the diagnosis process. The performance often does not meet the requirements, and some of the controllers are disconnected. With the gateway as a key component, the request end sends a heartbeat message, which is forwarded to multiple components through the gateway, which can keep the link from being disconnected, and concurrent diagnosis can be carried out normally. It is possible to diagnose at least one basic parameter data and fault code in the basic operating data one by one according to the knowledge graph, and to diagnose multiple related components.

[0023] In some embodiments of the present invention, step S101 includes: When a vehicle breaks down, the fault collection command is determined based on the fault location; According to the fault collection command, the vehicle's fault code is obtained.

[0024] In a specific embodiment of the present invention, if a vehicle breaks down, it is necessary to collect certain specific signals, such as the fault location. This requires issuing a fault collection command in the cloud based on the fault location. After the vehicle receives the fault collection command, it collects the required signals in the form of questions and answers to obtain fault codes. Fault codes are very important for diagnosis. Real-time collection of fault code information can quickly determine whether the vehicle is in normal condition.

[0025] In some embodiments of the present invention, Figure 2 As shown, step S102 includes: S201, updating the knowledge base according to historical data to obtain an initial knowledge base; S202, constructing a diagnosis model based on the fault analysis model, the multi-fault reasoning model, and the fault prediction model; S203. Construct a knowledge graph based on the diagnostic model and the initial knowledge base.

[0026] In a specific embodiment of the present invention, a knowledge base can be set up. The knowledge base can be set up according to actual conditions. The embodiment of the present invention is not limited here. Historical data can be processed, and then the knowledge base can be updated based on the processed data. For example, the processed data is stored in the knowledge base to update the data in the knowledge base, so that an initial knowledge base can be obtained.

[0027] In some embodiments of the present invention, the historical data includes image data and initial text data, such as Figure 3 As shown, step S201 includes: S301, identifying image data to obtain image knowledge; S302, converting the image knowledge to obtain image text data; S303, extracting knowledge from the initial text data and the image text data respectively to obtain corresponding knowledge ontologies; S304, performing quality assessment on the knowledge ontology and obtaining an assessment result; S305: Storing the target text data with qualified evaluation results in the knowledge base to obtain an initial knowledge base.

[0028] In a specific embodiment of the present invention, the host vehicle manufacturer inputs knowledge, including information such as maintenance manuals, historical maintenance data, maintenance data, fault cases, technical improvement plans and fault diagnosis technical data, and then intelligently identifies the input knowledge. The input knowledge types include image data and initial text data, etc. Image recognition technology is used to identify the knowledge in the image data to obtain image knowledge, which is converted into text data to obtain image text data; then knowledge can be extracted from the image text data and the initial text data respectively to obtain entities, attributes, and relationships between entities. For example, the entity can be a fault code, and the attribute relationship between the fault code and the fault code can be obtained. On this basis, a knowledge ontology is formed, that is, a basic unit such as entity-relationship-entity; for the new knowledge that has been integrated, it needs to go through a knowledge processing process, and the knowledge processing is quality assessment, that is, after the quality assessment, the part of the target text data with a qualified assessment result is added to the knowledge base to obtain an initial knowledge base to ensure the quality of the knowledge base.

[0029] Furthermore, models such as a fault analysis model, a multi-fault reasoning model, and a fault prediction model can be configured. These models are then used to construct a diagnostic model. The fault analysis model provides users with priority recommendations for possible fault causes and troubleshooting solutions (based on probability and troubleshooting order recommendations)—a fault tree machine learning (probability) model. The multi-fault reasoning model uses a multi-fault code and fault phenomenon inference engine to identify primary faults and new fault causes and prioritize diagnostic processes—a multi-fault tree machine learning inference engine. The fault prediction model uses a physical model analysis (including big data threshold evaluation) based on vehicle interaction data (fault codes, data streams, dynamic testing, etc.) to assist users in locating fault causes—a fault troubleshooting inference engine (decision tree) and a lock-in rate machine learning model. All three models are assisted and automated decision-making models based on physical models. The embodiments of the present invention can add or reduce models based on actual circumstances. The specific number and type of models can be set based on actual circumstances and are not limited by the embodiments of the present invention. A knowledge graph can then be constructed based on the diagnostic model and the initial knowledge base.

[0030] Furthermore, based on the experience of experts, claim records and diagnosis and repair data, new knowledge needs to be integrated into the initial knowledge base to dynamically update and adjust the knowledge graph.

[0031] In some embodiments of the present invention, the basic operation data further includes at least one key parameter data, and after step S102, the following steps are further included: Generate corresponding diagnostic instructions based on the diagnostic SDK and at least one key parameter data; According to the diagnostic instructions and knowledge graph, the corresponding key parameter data is deeply diagnosed to obtain the diagnostic results.

[0032] In a specific embodiment of the present invention, diagnosis is divided into basic parameter diagnosis and key parameter diagnosis. S103 is basic parameter diagnosis. Specifically, information on components that have a significant impact on vehicle safety and performance is collected in real time to obtain basic parameter data, mainly information on the engine, gearbox, headlights, and doors. This process is time-consuming and allows for rapid acquisition of basic parameter data. Basic parameter diagnosis can then be performed on the basic parameter data and fault codes one by one based on the knowledge graph, thereby determining the vehicle's operating status, i.e., obtaining a diagnostic result corresponding to each basic parameter data. Furthermore, the diagnostic result corresponding to each basic parameter data can be obtained. The basic operating data can also include at least one key parameter data, such as data on door opening and closing, data on headlight opening and closing, etc., so that a key parameter diagnosis, i.e., an in-depth physical examination, can be performed. The in-depth physical examination requires the development of a supporting physical examination script by the domain controller. Based on the diagnostic SDK, a diagnostic instruction corresponding to each key parameter data is sent and forwarded to the domain controller via the gateway. The domain controller executes a specific physical examination process based on the diagnostic instruction and the knowledge graph, thereby performing an in-depth diagnosis on each key parameter data and obtaining a diagnostic result for each key parameter data. This process is time-consuming and requires a long wait before obtaining a diagnostic result.

[0033] In some embodiments of the present invention, step S104 includes: When the fault parameter data indicates that the software of a component fails, the software of the component is upgraded based on the OTA technology to obtain the upgraded target software.

[0034] In a specific embodiment of the present invention, it is possible to determine whether the diagnosis result indicates a fault. If not, it indicates that the vehicle has no fault. If so, it indicates that the vehicle has a fault. Then, based on the judgment result, the location and data of the fault can be determined, that is, the fault parameter data can be obtained. The fault parameter data can be a fault in the basic parameter data, or a fault in the basic software or application software of the component. During the diagnosis process, if it is found that the basic parameters of certain components are incorrect, it can be determined that the fault parameter data is a fault in the basic parameter data. Then, OTA technology can be used to correct the parameters of certain components so that the components operate normally. If, during the diagnosis process, it is diagnosed that there is a problem with the basic software or application software of the component, it can be determined that OTA technology can be used to upgrade the component software to restore the function of the component to normal or to make the component have richer functions.

[0035] In some embodiments of the present invention, the method further comprises: Train and update the knowledge graph based on basic operating data to obtain an updated knowledge graph; Generate vehicle diagnostic intelligent after-sales service based on the updated knowledge graph.

[0036] In a specific embodiment of the present invention, after obtaining the knowledge graph, the knowledge graph and the diagnostic model in the knowledge graph can be updated based on basic operating data and image recognition technology. Specifically, regular content training can be performed to improve the knowledge graph, and then combined with the construction capabilities of the diagnostic model, vehicle diagnostic intelligent after-sales can be generated. Diagnostic intelligent after-sales can provide intelligent search for vehicle-side fault problems for the car manufacturer's customer service; it can also intelligently recommend vehicle usage suggestions, fault handling suggestions, and maintenance suggestions to the car owner; it can also intelligently push diagnostic solutions, maintenance solutions, and repair verification solutions to service technicians to achieve intelligent diagnosis and improve service satisfaction and one-time repair rate.

[0037] Further, such as Figure 4 As shown, after the vehicle where the tbox is located is powered on, it first registers with the cloud service platform. Diagnostic and maintenance processing can be performed on successfully registered vehicles. Specifically, data collection and diagnosis can be set up on the cloud service platform. Core knowledge graph. Remote OTA upgrades and fault query functions; the diagnostic app on the mobile phone obtains vehicle physical examination information by binding the vehicle's VIN code; on the diagnostic app, you can perform a one-click physical examination, and then click the general physical examination function to obtain key vehicle information. The key information is checked through the gateway VDCU. The key information can be multiple parameter information. The waiting time for the physical examination result is short, and the general operating status of the vehicle can be initially understood. To further understand the vehicle status, you can perform an in-depth physical examination function. The key components of the vehicle, mainly the lights, doors, and engine, can be deeply inspected. A single controller can be tested, and the gateway VDCU can be used to test multiple related controllers, such as the BDCU, PDCU, and IDCU. In-depth physical examinations require a long waiting time for the physical examination results. After a vehicle malfunctions, such as insufficient power, the vehicle needs to be inspected through the App. First, a certain fault phenomenon needs to be selected, such as insufficient power. For this fault phenomenon, the diagnostic system calls the knowledge engine model library for intelligent analysis, analyzing several key data, such as intake pressure, rail pressure, exhaust pressure, etc., to see which values ​​are abnormal. For the actual abnormal data, the cloud knowledge base is associated, and the probability of the fault cause is statistically analyzed using big data to recommend the initial probability of various faults, such as 1. Air filter blockage and probability; 2. Supercharger failure and probability; based on the probability of the fault cause and the ease of use and effectiveness of the detection method, a comprehensive analysis is conducted to recommend the optimal detection method; the detection results are fed back to the intelligent reasoning engine, and the detection results are used as judgment conditions for re-inference to accurately locate the cause and complete the model's self-learning process.

[0038] In order to better implement the vehicle fault detection and maintenance method in the embodiment of the present invention, based on the vehicle fault detection and maintenance method, the embodiment of the present invention also provides a vehicle fault detection and maintenance device, such as Figure 5 As shown, the vehicle fault detection and maintenance device 500 includes: The data acquisition module 501 is used to acquire the historical data of the host vehicle manufacturer and the basic operating data of the vehicle; the basic operating data includes at least one basic parameter data and a fault code; A graph construction module 502, configured to construct a knowledge graph based on historical data; The diagnosis determination module 503 is used to diagnose at least one basic parameter data and fault code in the basic operation data one by one according to the knowledge graph to obtain a diagnosis result corresponding to each basic parameter data; The fault correction module 504 is configured to determine fault parameter data and correct the fault parameter data when the diagnosis result indicates that a fault exists.

[0039] The vehicle fault detection and maintenance device 500 provided in the above embodiment can implement the technical solution described in the above vehicle fault detection and maintenance method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above vehicle fault detection and maintenance method embodiment, which will not be repeated here.

[0040] like Figure 6 As shown, the present invention also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602 and a display 603. Figure 6 Only some of the components of the electronic device 600 are shown, but it should be understood that implementation of all of the shown components is not required, and more or fewer components may be implemented instead.

[0041] In some embodiments, the memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. In other embodiments, the memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 600.

[0042] Furthermore, the memory 602 may include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store application software installed in the electronic device 600 and various data.

[0043] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 602 , such as the vehicle fault detection and repair method of the present invention.

[0044] In some embodiments, the display 603 can be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 603 is used to display information about the electronic device 600 and to display a visual user interface. Components 601-603 of the electronic device 600 communicate with each other via a system bus.

[0045] In some embodiments of the present invention, when the processor 601 executes the vehicle fault detection and maintenance program in the memory 602, the following steps may be implemented: Obtain historical data from the host vehicle manufacturer and basic operating data of the vehicle; basic operating data includes at least one basic parameter data and fault code; Build a knowledge graph based on historical data; Diagnose at least one basic parameter data and fault code in the basic operating data one by one according to the knowledge graph, and obtain a diagnosis result corresponding to each basic parameter data; When the diagnosis result shows that a fault exists, fault parameter data is determined and the fault parameter data is corrected.

[0046] It should be understood that, when the processor 601 executes the vehicle fault detection and maintenance program in the memory 602 , in addition to the above functions, it can also implement other functions. For details, please refer to the description of the corresponding method embodiment above.

[0047] Furthermore, the embodiments of the present invention do not specifically limit the type of electronic device 600 mentioned. The electronic device 600 may be a portable electronic device such as a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, or laptop computer. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The portable electronic devices mentioned above may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 600 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0048] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the vehicle fault detection and maintenance method steps or functions provided in the above-mentioned method embodiments can be implemented.

[0049] Those skilled in the art will appreciate that all or part of the process flow of the above-described method embodiment can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0050] The vehicle fault detection and repair method and device provided by the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A vehicle fault detection and maintenance method, characterized in that: include: Obtain historical data from the host vehicle manufacturer and basic operating data of the vehicle; The basic operation data includes at least one basic parameter data and a fault code; Building a knowledge graph based on the historical data; Diagnose the at least one basic parameter data and the fault code in the basic operation data one by one according to the knowledge graph to obtain a diagnosis result corresponding to each basic parameter data; When the diagnosis result indicates that a fault exists, fault parameter data is determined and the fault parameter data is corrected.

2. The vehicle fault detection and maintenance method according to claim 1, characterized in that: The constructing of a knowledge graph based on the historical data includes: The knowledge base is updated according to the historical data to obtain an initial knowledge base; Construct a diagnosis model based on the fault analysis model, multi-fault reasoning model and fault prediction model; A knowledge graph is constructed based on the diagnostic model and the initial knowledge base.

3. The vehicle fault detection and maintenance method according to claim 2, characterized in that: The historical data includes image data and initial text data, and the knowledge base is updated according to the historical data to obtain an initial knowledge base, including: Recognizing the image data to obtain image knowledge; Converting the image knowledge to obtain image text data; respectively extracting knowledge from the initial text data and the image text data to obtain corresponding knowledge ontology; Performing quality assessment on the knowledge ontology to obtain an assessment result; The target text data with qualified evaluation results is stored in the knowledge base to obtain an initial knowledge base.

4. The vehicle fault detection and maintenance method according to claim 1, characterized in that: The basic operation data also includes at least one key parameter data, and after the knowledge graph is constructed based on the historical data, it also includes: Based on the diagnostic SDK and the at least one key parameter data, generating a corresponding diagnostic instruction; According to the diagnostic instructions and the knowledge graph, an in-depth diagnosis is performed on the corresponding key parameter data to obtain a diagnostic result.

5. The vehicle fault detection and maintenance method according to claim 1, characterized in that: The method further comprises: When the vehicle fails, a fault collection command is determined according to the fault location; According to the fault collection command, a fault code of the vehicle is obtained.

6. The vehicle fault detection and maintenance method according to claim 1, characterized in that: The correcting the fault parameter data comprises: When the fault parameter data indicates that a software fault occurs in a component, the software of the component is upgraded based on the OTA technology to obtain an upgraded target software.

7. The vehicle fault detection and maintenance method according to claim 1, characterized in that: The method further comprises: Training and updating the knowledge graph according to the basic operation data to obtain an updated knowledge graph; According to the updated knowledge graph, the diagnostic intelligent after-sales of the vehicle is generated.

8. A vehicle fault detection and maintenance device, characterized in that: include: Data acquisition module, used to obtain historical data of the host vehicle factory and basic operation data of the vehicle; The basic operation data includes at least one basic parameter data and a fault code; A graph construction module, used to construct a knowledge graph based on the historical data; A diagnosis determination module, configured to diagnose the at least one basic parameter data and the fault code in the basic operation data one by one according to the knowledge graph, and obtain a diagnosis result corresponding to each basic parameter data; The fault correction module is used to determine fault parameter data and correct the fault parameter data when the diagnosis result shows that a fault exists.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the vehicle fault detection and maintenance method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the vehicle fault detection and maintenance method according to any one of claims 1 to 7 are implemented.

Images